Skip to content

Quickstart

Jump to bottom
Sanni heruwala edited this page Jun 12, 2026 · 1 revision

Quickstart

Five minutes from zero to your first query. Three install paths — pick the one that fits your setup.

Option A: Docker (any OS)

docker run -d --name rednotebook \
  -p 8000:8000 \
  -v rednotebook-data:/data \
  ghcr.io/sanniheruwala/rednotebook-ai:latest

Open http://localhost:8000. Done.

With Docker Compose if you want to tune env vars:

git clone https://github.com/sanniheruwala/RedNotebookAI.git
cd RedNotebookAI
cp .env.example .env  # edit AI provider keys, auth, etc.
docker compose up -d

Option B: Python (pip)

pip install rednotebook-ai    # latest stable from PyPI
rednotebook run               # serves the FastAPI app on :8000

Then in another terminal, the dev frontend:

git clone https://github.com/sanniheruwala/RedNotebookAI.git
cd RedNotebookAI/frontend
npm install
npm run dev                   # :3000

The Docker image bundles a pre-built frontend; if you go pip-only and don't want to run Node, set REDNOTEBOOK_STATIC_DIR to a directory holding a Next.js static export.

Option C: From source

git clone https://github.com/sanniheruwala/RedNotebookAI.git
cd RedNotebookAI
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
cp .env.example .env
rednotebook run

# in another terminal
cd frontend && npm install && npm run dev

This is the path you want if you're going to contribute. See Contributing.

Your first query

  1. App opens. The default connection is DuckDB · in-memory — no setup required.

  2. Click the blank notebook in the canvas. Type into the SQL cell:

    SELECT
  'hello' AS greeting,
  42      AS the_answer,
  CURRENT_DATE AS today

  3. Hit ⌘↵ (or click Run). Result appears below.

  4. Click the Profile tab — per-column stats + sparkline histograms.

  5. Click Summarize result — AI brief based on the data (configure an AI provider in admin settings for richer output; mock is the default).

That's the loop. Everything else is variations on it.

Next steps

Clone this wiki locally